import requests
from bs4 import BeautifulSoup
def trade_spider(max_page):
page = 1
i = 0
while page <= max_page:
url = 'https://www.thenewboston.com/search.php?type=0&sort=reputation&page=' + str(page)
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for link in soup.findAll('a',{'class':'desc-title'}):
href = 'https://www.thenewboston.com'+ link.get('href')
title = link.string
print(title)
print(href)
i += 1
print('\n')
page += 1
print(i)
trade_spider(5)
Web_Crawler
最新推荐文章于 2022-04-27 12:21:16 发布